This is a guest post from Mike Montemorra, who is a technology guru with long and successful career in computer industry. Mike keeps an eye on the latest developments in computer and storage technology and publishes his observations weekly. Below is his brief summary of what was important in the past week.
What did we learn last week?
Hi everyone and Happy New Year to all!
This year has good things in store for all of us in the storage end of the business, of that I am sure, so let’s get going!
In case you haven’t seen this already, this is a very well written summarization of current HDD HAMR vs MAMR technologies.
The ‘winner’, of course, will be the company that makes the most money or can recoup some or all of their copious investments. WD made its announcement that 16TB MAMR drives were ‘sampling’ at CES this week. I will be more impressed when they announce customer design wins and release some reliability data.
… and conventional HDD’s are still being announced with the recent Toshiba MG08 16TB drive. I suppose we all knew that 16TB was inevitable given the 9D helium platform they have. Others will probably follow suit since this is the path off least resistance toward higher capacity without ‘energy assist’ (MAMR or HAMR) products which will probably ramp up more slowly to provide a solid reli base for customer confidence.
The GreyBeards are at it again with a year-end CY18 summary report. It’s interesting and probably predictive of trends for CY19.
… and Storage Newsletter has their predictions for CY19 as well (part 1 and part 2). They say object storage is dead and composable infrastructure is emerging (what would be really interesting is compostable storage, but that may not be in the cards!)
Here’s an interesting paper on how STT-MRAM might evolve in coming years.
The first step in further increases in speed for these STT junctions is precise control of higher order spin waves. There are potentially other uses besides memory for these kinds of spintronic devices.
This week’s CES 2019 show was big and somewhat eventful, but there were no major groundbreaking announcement in storage besides the ones I’ve mentioned here. Here is a decent summary of the show.
A company that is definitely getting its mojo back, AMD now has the largest number of announced 7nm-based CPU/GPU designs. Nice work!
Using terahertz exitation to switch topological materials is an emerging and quite interesting area of physics that has yet to be exploited and could easily be commercialized. Stay tuned for developments.
IBM just introduced a shiny new quantum computer, the first of its kind they claim, but only accessable via the IBM cloud. Guess you will have to admire this beauty from afar. Perhaps their tight controls on the qubits will improve the error rate and repeatability of computations… we will just have to wait and see.
… and while we are on the subject of quantum computing, there was also an interesting article on using quantum computers to do ‘quantum chemistry’ calculations. Maybe these Osaka researchers can use that IBM QC to do some real science!
Source: SpiNNaker (Univ of Manchester)
A million cores in one place and working together? Wow! In this high stakes compute game, the next guy will raise that million by another million.. and so on.
Here’s an interesting development relating to Fuze card use by crooks. You’ve got to hand it to them, creativity is one of their strong suits.